A digital twins enabled underwater intelligent internet vehicle path planning system via reinforcement learning and edge computing

The Autonomous Underwater Glider(AUG)is a kind of prevailing underwater intelligent internet vehicle and occupies a dominant position in industrial applications,in which path planning is an essential problem.Due to the complexity and variability of the ocean,accurate environment modeling and flexible path planning algorithms are pivotal challenges.The traditional models mainly utilize mathematical functions,which are not complete and reliable.Most existing path planning algorithms depend on the environment and lack flexibility.To overcome these challenges,we propose a path planning system for underwater intelligent internet vehicles.It applies digital twins and sensor data to map the real ocean environment to a virtual digital space,which provides a comprehensive and reliable environment for path simulation.We design a value-based reinforcement learning path planning algorithm and explore the optimal network structure parameters.The path simulation is controlled by a closed-loop model integrated into the terminal vehicle through edge computing.The integration of state input enriches the learning of neural networks and helps to improve generalization and flexibility.The task-related reward function promotes the rapid convergence of the training.The experimental results prove that our reinforcement learning based path planning algorithm has great flexibility and can effectively adapt to a variety of different ocean conditions.

A Ray Tracing and Joint Spectrum Based Clustering and Tracking Algorithm for Internet of Intelligent Vehicles

Driven by the rapid growth in information services provided by the Internet and the appearance of new multimedia applications,millimeter wave is foreseen as a key enabler towards the Internet of intelligent vehicles(IoIV)for urban traffic safety enhancement.In this regard,cluster-based channel modeling has become an important research topic in the realm of emergency communications.To fully understand the cluster-based channel model,a series of vehicle-to-infrastructure(V2I)channel simulations at 22.6 GHz are conducted by a three-dimensional ray tracing(RT)simulator.The clustering and tracking algorithm is proposed and analyzed from three aspects by the obtained simulation results.The multiple signal classification estimation spectrum is applied to restrain the influence of antenna sidelobes and identify targets at first.Based on the fundamentals,the clusters can be identified and subsequently tracked using the proposed approach.The impacts of antenna sidelobes,angle resolution of beam rotation,and non-line-of-sight propagation path on the performance of clustering and tracking are evaluated.The multi-component-level RT results are adopted as comparison benchmarks,which reflect the ground truth.This work aims to provide a full picture of the clustering characteristics for designing and analyzing emergency communication systems.